怎么看待CSDN把网上已有的免费资料收录为己有然后需积分下载？

import subprocess import sys from flask import Flask, request, jsonify import os from selenium import webdriver from selenium.webdriver.chrome.service import Service from article import CsdnData from selenium.webdriver.chrome.options import Options import logging import configparser import osutils config = configparser.ConfigParser() config.read('config.ini',encoding='utf-8') logger = logging.getLogger() logger.setLevel(logging.INFO) # 创建文件处理器 file_handler = logging.FileHandler('app.log') file_handler.setLevel(logging.INFO) file_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')) # 创建流处理器 stream_handler = logging.StreamHandler() stream_handler.setLevel(logging.INFO) stream_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')) # 将处理器添加到日志记录器 logger.addHandler(file_handler) logger.addHandler(stream_handler) app = Flask(__name__) @app.route('/csdn/article/download', methods=['POST']) def article_download(): logger.info("当前请求参数是："+str(request.get_json())) try: if request.content_type == 'application/json': # 处理JSON格式的数据 data = request.get_json() article_url = data.get('article_url') download_url = data.get('download_url') receiver_email = data.get('receiver_email') format = data.get('format') # 创建一个Chrome选项对象 chrome_options = Options() service = Service(config['DEFAULT']['ChromeDriverPath']) #启动本地Chrome浏览器不启动无痕方式 (直接避过登录) chrome_options.add_argument(f'user-data-dir={config['DEFAULT']['WindowsProfilePath']}') driver = webdriver.Chrome(options=chrome_options,service=service) directory_path = config['DEFAULT']['DirectoryPath'] try: csdnDate = CsdnData(driver) # 根据类型判断是下载文章还是下载资源 if article_url: csdnDate.get_article(article_url,format,directory_path,logger) else: csdnDate.get_download(download_url,logger) # 下载完成后发送邮件 if osutils.is_download_completed(directory_path, logger): latest_file_path = osutils.get_latest_file(directory_path, logger) #发送邮件 osutils.send_mail(config['DEFAULT']['Email'],config['DEFAULT']['AuthCode'],receiver_email,latest_file_path,logger) driver.quit() except RuntimeError as runtimeError: logger.error(f"下载文章失败,错误内容为：{runtimeError}") driver.quit() osutils.send_error_mail(config['DEFAULT']['Email'], config['DEFAULT']['AuthCode'], receiver_email, str(runtimeError), logger) return str(runtimeError), 504 return '下载完毕，已发送至邮箱，请查收！', 200 else: return '提交数据格式不正确',403 except Exception as e: logger.error(f"下载文章失败,错误内容为：{e}") # 发送邮件 osutils.send_mail(config['DEFAULT']['Email'], config['DEFAULT']['AuthCode'], receiver_email, "下载异常，请联系管理员解决", logger) return "下载异常，请联系管理员解决", 503 finally: # 杀掉Chrome进程确保下一次请求不受影响 os.system('taskkill /f /im chrome.exe') if __name__ == '__main__': # 定义需要安装的模块列表 required_packages = ['flask', 'requests','selenium'] # 检查每个模块是否已安装，未安装的将使用pip安装 for package in required_packages: try: # 尝试导入模块 __import__(package) except ImportError: # 如果模块未安装，使用pip安装 print(f"安装模块：{package}") subprocess.check_call([sys.executable, "-m", "pip", "install", package]) app.run(host='0.0.0.0',debug=True,port=5000)

# csdn 资料处理类 import os import time from selenium.webdriver.common.by import By from selenium.webdriver import ActionChains class CsdnData: def __init__(self, driver): self.driver = driver #检查链接是否是csdn的文章链接 def check_articleurl(self, url): if 'csdn.net' in url: return True if 't.csdnimg.cn'in url: return True return False def check_downloadurl(self, url): if 'download.csdn.net' in url: return True return False # 检查是否具备查看的文章权限 def check_permission(self, page_source): if '订阅专栏解锁全文' in page_source: return False return True # 检查是否具备下载权限 def check_download(self, page_source): if "VIP专享下载" in page_source or "立即下载" in page_source: # 判断下载内容是否超过50MB file_size_span = self.driver.find_element(By.XPATH, '/html/body/div[3]/div/div[1]/div/div[2]/div[1]/div[1]/div[2]/div[1]/div[1]/div/div[2]/div[2]/div/span[7]') # 获取其中文本 file_size = file_size_span.text # 判断其中是否含有 KB 或者MB 等单位 if 'MB' in file_size: # 获取其中的数字 file_size = float(file_size.replace('MB', '').strip()) if file_size > 50: raise RuntimeError("暂不支持下载文件超过50MB,如有需要可以联系管理员手动帮忙下载，微信：") elif 'KB' in file_size: pass else: # 判断下载内容是否超过50MB file_size_span = self.driver.find_element(By.XPATH, '/html/body/div[3]/div/div[1]/div/div[2]/div[1]/div[1]/div[2]/div[1]/div[1]/div/div[2]/div[2]/div/span[6]') # 获取其中文本 file_size = file_size_span.text if 'MB' in file_size: # 获取其中的数字 file_size = float(file_size.replace('MB', '').strip()) if file_size > 50: raise RuntimeError("暂不支持下载文件超过50MB,如有需要可以联系管理员手动帮忙下载，微信：") return True def try_download_file(self,logger): # 点击立即下载按钮 try: download_button = self.driver.find_element(By.XPATH, '/html/body/div[3]/div/div[1]/div/div[3]/div[1]/div[1]/div[2]/div[1]/div[3]/div[1]/button/span/span') download_button.click() except Exception as e: logger.info("点击下载按钮出错，正在重试") download_button = self.driver.find_element(By.XPATH, "/html/body/div[3]/div/div[1]/div/div[2]/div[1]/div[1]/div[2]/div[1]/div[3]/div[1]/button/span/span") download_button.click() logger.info("点击下载按钮") time.sleep(2) # 在弹窗页面中找到VIP专享下载按钮 try: vip_download_button = self.driver.find_element(By.XPATH, '/html/body/div[3]/div/div[1]/div/div[4]/div/div[3]/div/div/button') vip_download_button.click() except Exception as e: try: logger.info("点击VIP专享下载按钮出错，正在重试") vip_download_button = self.driver.find_element(By.XPATH, "/html/body/div[3]/div/div[1]/div/div[3]/div/div[3]/div/div/button") vip_download_button.click() except Exception as e: logger.error(f"点击VIP专享下载按钮出错，错误内容为：{e}") self.driver.quit() os.system('taskkill /f /im chrome.exe') raise RuntimeError("Csdn账号今天已达到下载上限啦~ 该功能明天再开放! （文章浏览功能正常使用中）") logger.info("点击VIP专享下载按钮,开始下载文件...") time.sleep(3) def get_article(self, url,format,directory_path,logger): if not self.check_articleurl(url): raise RuntimeError("链接不是csdn的文章") self.driver.get(url) #获取请求后的页面源码 page_source = self.driver.page_source #检查是否具备查看的文章权限 check_permission = self.check_permission(page_source) if not check_permission: raise RuntimeError("专栏文章,没有查看文章的权限") ActionChains(self.driver).send_keys('aa').perform() time.sleep(3) ActionChains(self.driver).send_keys('sr').perform() time.sleep(2) if format == 'screenshot': # 获取目录中的所有文件和文件夹 files_and_folders = os.listdir(directory_path) # 当前文件中的个数 file_num = len(files_and_folders) ActionChains(self.driver).send_keys('pg').perform() # 由于导出图片功能不一定能够成功，所以需要计数如果检查超过30秒仍然没有导出图片，那么就认为导出失败 start_time = time.time() while True: files_and_folders = os.listdir(directory_path) if len(files_and_folders) > file_num: break if time.time() - start_time > 30: logger.info(f"导出图片失败") raise RuntimeError("导出图片失败") time.sleep(1) logger.info(f"当前图片正在下载中...") else: ActionChains(self.driver).send_keys('oh').perform() time.sleep(3) def get_download(self,url,logger): # 检查url链接是否有问题 if not self.check_downloadurl(url): raise RuntimeError("链接不是csdn的下载链接") #获取请求后的页面源码 self.driver.get(url) # 获取请求后的页面源码 page_source = self.driver.page_source # 检查页面是否具备下载的权限 self.check_download(page_source) # 尝试下载文件 self.try_download_file(logger)

import os import time from csdnreptiles.qqemail import QQMailer # 检查下载是否完成 def is_download_completed(download_dir,logger): # 循环检查下载文件夹中是否还有临时文件 while any([filename.endswith(".crdownload") for filename in os.listdir(download_dir)]): # 找到存在的crdownload文件 for filename in os.listdir(download_dir): if filename.endswith(".crdownload"): logger.info(f"存在crdownload文件: {filename} 下载中...") time.sleep(1) # 等待1秒再次检查 return True # 获取目录中最新的文件 def get_latest_file(directory_path,logger): # 获取目录中的所有文件和文件夹 files_and_folders = os.listdir(directory_path) # 过滤出文件列表 files = [f for f in files_and_folders if os.path.isfile(os.path.join(directory_path, f))] # 初始化最新文件的时间戳和路径 latest_timestamp = 0 latest_file_path = None # 遍历文件列表，找到最新生成的文件 for file in files: file_path = os.path.join(directory_path, file) file_timestamp = os.path.getmtime(file_path) # 获取文件最后修改时间的时间戳 if file_timestamp > latest_timestamp: latest_timestamp = file_timestamp latest_file_path = file_path # 打印最新生成的文件路径 logger.info(f"最新生成的文件路径: {latest_file_path}") return latest_file_path # 发送邮件 def send_mail(sender,auth_code,receiver_email,latest_file_path,logger): mailer = QQMailer(sender, auth_code) mailer.send_mail( receiver_email=receiver_email, subject="csdn资源助手", body="csdn文章资源自助服务内容，请在附件中查看您的文章内容", attachment_path=latest_file_path ) logger.info("邮件发送成功！") def send_error_mail(sender,auth_code,receiver_email,notes,logger): mailer = QQMailer(sender, auth_code) mailer.send_mail( receiver_email=receiver_email, subject="csdn资源助手", body="csdn文章资源自助服务内容，下载失败,失败原因:"+notes, ) logger.info("已邮件通知下载失败!")

[DEFAULT] # Chrome浏览器驱动路径 ChromeDriverPath = # Chrome浏览器安装地址 windowsProfilePath = DirectoryPath = SMTPServer = smtp.qq.com # 发送人的QQ邮箱 Email = # 发送人QQ邮箱授权码 AuthCode =